Fastest
Eureka on the web
When you want the answer in the next five minutes.
The agent works the prompt against patents and technical literature, citing every source.
Run your analysis now →https://eureka.patsnap.com/resources/blog/rd-blog/semantic-segmentation-encoder-decoder-network-architecture-patent-landscape/ · Patsnap · data cut-off 2026-10-27 · downloaded from the live page
Patent Landscape · AI & Machine LearningSemantic Segmentation Encoder-Decoder Network Architecture Patents
222 patent families on semantic segmentation encoder-decoder networks, spanning filers from Hohai University to Qualcomm, with IPC and filing trend data.
346
Published Records
222
Simple Patent Families
2%
Families Naming the Largest Filer
45%
In Force at Cut-off
346 published records collapse into 222 simple (DOCDB) families; the difference is the same invention filed in more than one country. HOHAI UNIV is named on 5 of the 222 patent families in scope. One patent family can name several filers, so these figures are not slices of a divided whole and do not add up. In force = 155 of 346 records still granted and maintained at the data cut-off; the rest are pending, withdrawn, refused or lapsed.
- 222 simple patent families and 346 published records match this search, with no single row holding more than a 2.3% share of families.
- 80 of the 91 listed filers hold 2 or fewer simple patent families each, pointing to a long tail of small-volume entrants.
- G06N and G06V subclasses appear on 77.9% and 67.1% of the 222 families respectively, the two largest shares in the technology split.
Published byPatsnap Research··6 min readSourced from Patsnap Eureka
Overview
What this search covers
This landscape covers 222 simple patent families (346 published records) returned by a search for semantic segmentation work described together with an encoder-decoder network architecture. The search string requires both terms to appear in the title, abstract or claims, so it captures filings that explicitly frame the architecture in encoder-decoder terms rather than every semantic segmentation filing in general.
No date limit was applied to the search, so the set spans whatever years the matching records happen to fall in. The filing-trend chart below shows a recent window only and should be read with that in mind, since the most recent years are still filling in as filings publish.
Records vs. families in scope
Ordered by volume only, not by importance or claim strength. Counted in simple (DOCDB) patent families, so one invention filed in several countries counts once. Names come from Patsnap's standardised assignee field as recorded on each document; subsidiaries and group companies are not merged. The icon before each name is read from the name itself (words such as University, Institute or Ltd); the data carries no organisation-type field, so treat it as a reading aid rather than a classification. 2 rows in this table start with the same name (GUILIN UNIVERSITY OF TECHNOLOGY, GUILIN UNIV OF ELECTRONIC TECH). They are left as separate rows, so the largest-filer figure above is per legal entity, not per group. Rows that look related still cannot be added together: one family can name several of them. Counted one by one, those rows between them cover more than the largest single row does, so the largest single row is not necessarily the largest filer in this field. How much those rows cover together is not something this dataset can say: one family can name several of them, so their counts cannot be added. Every ranking statement on this page is per individual filer row, never per group. Filings held by named individuals rather than organisations are removed where they can be identified (9 here); that identification is not exhaustive, so an individually held filing can still appear below. Either way those filings stay inside the totals above. This table shows the top 30 of the 91 filers returned for this search; the data endpoint returns at most 100 entities, so even that 91 is not the complete set of filers. A single family can name more than one filer, so these counts overlap and do not add up to the total.
Source: Patsnap Eureka. Assignee ranking and totals. Derived from one Patsnap search for Semantic Segmentation Encoder-Decoder Network Architecture Patent Landscape, covering all matching records regardless of filing date (the search string sets no date limit), retrieved 2026-10-27. Counts cover published records only and move as new filings publish.Run this in Eureka MCP
The data
Filing trend and technology composition
Two views of the same 222 families: how filing activity by earliest filing year shows up in published records, and which IPC subclasses the underlying documents carry.
Filing trend, 2016–2026 (published records)
Published records rose from 2 in 2016 to a peak of 60 in 2025, with 2018 to 2021 recording a 70% increase from 27 to 46. 2021 is the most recent year treated as complete; 2022 onward is still filling in as filings publish, so the chart's recent downturn should not be read as a drop in filing activity.
Counted in published records by earliest filing year, not de-duplicated into families. A filing is counted in the year it was filed, but it only becomes visible after it publishes: roughly 18 months for most routes, and up to 30 months where a PCT application enters national phase. 2022 onwards are therefore still filling in and are shaded; no growth figure on this page uses them. Because this series counts documents rather than inventions, a rise can mean more inventions or the same inventions filed in more countries; this dataset cannot separate the two.
IPC subclass composition (share of 222 families)
G06N (computing based on AI models) appears on 77.9% of the 222 families and G06V (image/video recognition) on 67.1%, followed by G06T (image data processing and generation) at 38.7% and G06K (data recognition and presentation) at 15.8%. Because one family can carry several IPC classes, these shares add up to more than 100%.
Shares are the percentage of the 222 patent families in scope. One patent family can carry several IPC classes, so the shares add up to more than 100%.
Source: Patsnap Eureka. Filing trend and technology composition. Derived from one Patsnap search for Semantic Segmentation Encoder-Decoder Network Architecture Patent Landscape, covering all matching records regardless of filing date (the search string sets no date limit), retrieved 2026-10-27. Counts cover published records only and move as new filings publish.
Go deeper on Semantic Segmentation Encoder-Decoder Network Architecture Patent Landscape with Eureka
This page is one run against one query. Ask Eureka your own question about semantic segmentation encoder-decoder network architecture patent landscape and every answer comes back with the patent numbers behind it.
Try EurekaRecord in focus
A record from the result set
From the result set
WO2023102224A1, Data augmentation for multi-task learning for depth mapping and semantic segmentation
INNOPEAK TECHNOLOGY, INC.
Filed by Innopeak Technology, Inc., the application describes a computer applying an encoder-decoder network to a first image to extract depth and semantic information, identifying an object and a region of interest (ROI) from the semantic information, adjusting the ROI to generate a second image, and using that second image to train the encoder-decoder network.This is simply the first record returned under the database's default order, not the most cited, newest or broadest filing in the set.
Selected as the first record the search returns under the database default order, then shown in full. It is not ranked by citations, claim breadth or commercial importance, and it is not a judgement about which filing in this space matters most.
Source: Patsnap Eureka. The first record the search returned, shown in full. Derived from one Patsnap search for Semantic Segmentation Encoder-Decoder Network Architecture Patent Landscape, covering all matching records regardless of filing date (the search string sets no date limit), retrieved 2026-10-27. Counts cover published records only and move as new filings publish.Run this in Eureka MCP
Run it yourself
Put your own technology through the same analysis
Where to run it
For builders
MCP server & REST API
When it has to run inside your own pipeline.
Patent search, landscape analysis and assignee resolution as MCP tools. Drop them into any agent framework, or call REST directly.
Browse MCP servers →Insights
Reading the filer and technology data
Three figures worth sitting with before treating any single row as representative of the field.
Largest single filer row
5 of 222 families
Hohai Univ
2.3% of families named on the top row
Hohai Univ is named on 5 of the 222 simple patent families in scope, a 2.3% share. Two other rows (Guilin University of Technology and Guilin Univ of Electronic Tech) are listed separately and, counted one at a time, exceed this figure; they are not added together here because a family can name more than one filer.
Counted in simple patent families
Long tail
80 of 91
listed filers
Most listed filers hold 2 or fewer families
80 of the 91 listed filers hold 2 or fewer simple patent families each. The listed rows are organisations; individual-inventor filings sit inside the 222-family total but are not broken out in this list.
Counted in simple patent families, top 30 shown on page
Legal status at retrieval
155 of 346
records in force
45% of records were granted and in force
155 of the 346 published records (45%) were granted and still in force at the retrieval date. The remainder cover pending, withdrawn, refused, lapsed and not-determinable status, which this dataset does not break down further.
Counted in published records, status as of 2026-10-27
Receiving offices
17 offices
where records were filed
China and the US carry the largest counts
Across 17 receiving offices, the largest counts of published records were filed with China (149) and the United States (81), followed by India (37), the EPO (26), WIPO/PCT (17) and Australia (7). This reflects where applications were filed, not where any filer is based.
Counted in published records; one record can appear at more than one office
Eureka AI Agent
Looking for what nobody has claimed yet?
Eureka can read the same corpus for gaps instead of for coverage: under-claimed branches adjacent to semantic segmentation encoder-decoder network architecture patent landscape, with the prior art for and against each one.
Source: Patsnap Eureka. Derived observations on the same dataset. Derived from one Patsnap search for Semantic Segmentation Encoder-Decoder Network Architecture Patent Landscape, covering all matching records regardless of filing date (the search string sets no date limit), retrieved 2026-10-27. Counts cover published records only and move as new filings publish.Run this in Eureka MCP
What's next
Where to take this analysis
The figures here describe what the search returned. Eureka can help carry the same questions further into claim-level detail.
Read the granted claims directly
Family and abstract data cannot establish what any single filing blocks. Pull the granted claim set for any record that matters to a specific design before drawing conclusions about freedom to operate.
Explore in Patsnap Eureka →Track the filers beyond the top rows
With 80 of 91 listed filers holding 2 or fewer families, most of the activity in this set sits outside the largest rows. Monitoring new filings from smaller entrants may surface movement before it shows up in rankings.
Explore in Patsnap Eureka →Watch the still-filling years
2022 onward is understated in this dataset as filings continue to publish. Re-running this search periodically will give a more complete picture of recent filing activity.
Explore in Patsnap Eureka →Source: Patsnap Eureka. Suggested next steps. No new data: every figure named here is one of those above. Derived from one Patsnap search for Semantic Segmentation Encoder-Decoder Network Architecture Patent Landscape, covering all matching records regardless of filing date (the search string sets no date limit), retrieved 2026-10-27. Counts cover published records only and move as new filings publish.Run this in Eureka MCP
FAQ
Common questions about this landscape
This search returns 222 simple patent families, representing 346 published records once every country filing and re-publication is counted. The family figure is the better measure of distinct inventions, while the record figure counts each publication separately, including multiple filings of the same invention in different offices. No date limit was applied, so the set spans whatever years the matching documents happen to fall in, and the search string requires both semantic segmentation and encoder-decoder terminology to appear together in the title, abstract or claims.
Hohai Univ is named on 5 of the 222 simple patent families in scope, the largest count among any single listed row, a 2.3% share. Two further rows beginning with Guilin (Guilin University of Technology and Guilin Univ of Electronic Tech) are listed separately and are not summed with each other or with Hohai Univ, since one family can name more than one filer and any sum would over-count. Beyond the top rows, 80 of the 91 listed filers hold 2 or fewer families each, so filing activity in this set is spread across many entrants rather than concentrated in a handful of rows.
Published records rose from 27 in 2018 to 46 in 2021, a 70% increase over that three-year span, and the series continues to a peak of 60 records in 2025. However, 2022 onward is still filling in because of publication lag, up to 18 months for most routes and up to 30 months for PCT applications entering national phase, so the apparent plateau or dip in the most recent years should not be read as a slowdown. 2021 is the most recent year in this dataset that can be treated as reasonably complete.
Among the 222 simple patent families, G06N (computing based on AI models) appears on 77.9% and G06V (image/video recognition) on 67.1%, the two largest shares of any IPC subclass tracked here. G06T (image data processing and generation) appears on 38.7% and G06K (data recognition and presentation) on 15.8%. Because a single family can carry several IPC classes at once, these shares add up to more than 100%, and they describe classification overlap rather than four separate slices of the set.
Across 17 receiving offices captured in this dataset, the largest counts of published records were filed with China (149) and the United States (81), followed by India (37), the EPO (26), WIPO under the PCT (17) and Australia (7). These figures are counted in published records and reflect where applications were filed, not any filer's nationality or location, since this dataset carries no country-of-origin information for filers.
155 of the 346 published records, or 45%, were granted and still in force as of the retrieval date of 2026-10-27. The remaining records cover a mix of pending, withdrawn, refused, lapsed and not-determinable statuses that this dataset does not break down individually. Legal status changes continuously and should be checked against a live register before relying on it for any filing decision.
Answers are grounded in the same dataset. Derived from one Patsnap search for Semantic Segmentation Encoder-Decoder Network Architecture Patent Landscape, covering all matching records regardless of filing date (the search string sets no date limit), retrieved 2026-10-27. Counts cover published records only and move as new filings publish.Run this in Eureka MCP
Research Semantic Segmentation Encoder-Decoder Network Architecture Patent Landscape in depth with Eureka
Go past this page: query the whole semantic segmentation encoder-decoder network architecture patent landscape corpus yourself, in your own scope.
Every answer comes back with patent numbers you can open.
How this page was built, and what the numbers do and do not mean
Search. Every figure on this page comes from one Patsnap search, run once and not edited afterwards. This is the exact search string:
TAC:(("semantic segmentation") AND ("encoder-decoder" OR "encoder decoder" OR "encoder-decoder network"))Reading the field codes: TAC searches the title, abstract and claims of each record, not the full description. The search string sets no date limit, so the scope is every matching record in the database regardless of when it was filed. It is not restricted to recent years. How this string was built matters for how far the counts can be pushed. It was generated in batch from a topic list rather than hand-crafted for this page, and the result set is not manually screened. A keyword search over title, abstract and claims both over-captures (unrelated filings that happen to use the same words) and under-captures (the same invention written in different words). This page cannot measure either effect, so read every figure here as what this particular string returned, not as what exists in the field. One subclass (G06N) carries 77.9% of the patent families, so this search returned a classification-tight set.
What is being counted. Two different units appear on this page and they are not interchangeable. The filer list and the technology split are counted in simple (DOCDB) patent families: one invention counts once however many countries it was filed in. The total, the jurisdiction split and the filing-year chart are counted in published records: the same invention counts once per publication. For this search that is 346 records and 222 families. Record counts reward filing in many jurisdictions; family counts do not. Shares are only ever taken against a denominator in the same unit, and each one names it.
Who the filers are. Names come from Patsnap's standardised assignee field, as recorded on the documents themselves. They are not rolled up to corporate group: a parent and its subsidiaries appear as separate entries, and a portfolio acquired from another company stays under the name on the document unless the assignment is reflected there. This list is meant to carry organisations, not people. Filings held by a named individual are identified by matching the assignee against the inventors on the same search, and, for names written in Chinese, Japanese or Korean characters, by the name carrying no organisational suffix; those are removed from the list (9 of them here). Neither test is exhaustive: the inventor list it matches against is itself capped, and a personal name written in Latin script with no organisational wording in it cannot be told apart from a short company name by rule. So an individually held filing can still appear in the list. Those filings stay inside every total and share on this page either way, so the listed entries can add up to less than the total. A record shown in full further down still names its assignee exactly as the patent office records it, including where that is a person: that name is how the record is identified and checked. What is left out of the ranking is people as ranked entries, not people as cited sources. The table shows the top 30 of the 91 filers returned, ordered by count alone; the data endpoint returns at most 100 entities, so even that 91 is not every filer. One patent family can name several filers and each is counted separately, so these rows are not slices of a divided whole: adding them together over-counts, and this page deliberately publishes no combined "top five" share for that reason. See every filer, individuals included
Dates. The year chart counts by earliest filing year, not publication year. A filing only becomes visible once it publishes: roughly 18 months for most routes, and up to 30 months where a PCT application enters national phase. Measured across these pages, the year four back from today still holds only about 89% of its eventual count. 2022 onwards are therefore shaded on the chart as still filling in, and the growth figure stops at 2021. The data behind this page was retrieved on 2026-10-27.
Legal status. "In force" counts documents whose legal status at retrieval was granted and maintained (155 of 346). Everything else is pending, withdrawn, refused, lapsed or not determinable, and those states are not broken out here because the underlying codes do not separate them cleanly. Legal status changes continuously and is reported per document, not per family. Get the status breakdown in Eureka
Classification. The technology split uses IPC subclasses (four characters, for example H01M). A single record usually carries several, so the shares add up to more than 100% and a record can appear in more than one bar. Subclass is a coarse grouping; it describes the field a record was classified into, not what the claims cover. Break the classes down to subgroup level
Who wrote the words. The tables, charts, counts, shares and patent numbers on this page are produced directly from the search result by a program; none of them are written or estimated by a language model. The surrounding prose, headings, FAQ answers and the answers in the question panel are drafted by a language model that is given those same figures and is not permitted to introduce others. Prose can still mis-describe a correct figure, so where the two disagree, the tables and charts are the record.
Disclaimer. This page is generated from Patsnap Eureka data drawn from a limited snapshot of global patent and scientific-literature records, and is provided for general information and reference only.
Patent data carries limitations that apply to every figure above. Recent filings are under-counted, because an application is not public until roughly 18 months after filing and database loading adds further delay. The search string defines and constrains everything shown: records that use different terminology, or that sit outside the fields searched, are absent and cannot be counted. Applicant names, classification codes, legal-status codes and citation records are taken as recorded and may contain errors, duplicates, omissions or stale entries. Ordering by volume is not a measure of quality, scope, enforceability or commercial value, and a larger portfolio is not a stronger one. As a result, the analysis may be incomplete or inaccurate and may not reflect the full technology landscape.
Nothing on this page constitutes an exhaustive prior-art, novelty, freedom-to-operate, validity or infringement search, nor does it constitute legal, financial, investment, or professional advice, and it should not be relied upon as such. No attorney-client relationship is created by it. Any patent, commercial, or strategic decision should be verified independently against the primary records and reviewed with qualified patent, legal, and domain professionals. Patsnap makes no warranties, express or implied, as to the accuracy, completeness, or fitness for any particular purpose of the information presented.
The question panel. The answers behind the suggested questions on this page were written when the page was generated, not in response to your click. The progress steps that play before an answer appears are an animation of how that analysis was done; nothing is being searched or computed at that moment. Typing your own question instead opens Patsnap Eureka, which does run it live.
Machine translation. Assignee and organisation names originally recorded in Chinese, Japanese or Korean have been rendered into English by an AI translation step so that the tables stay readable. These renderings are best-effort and may not match a company's registered English name; the original name is what the underlying patent record carries, and it is what any Eureka query launched from this page uses.